{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.04610", "kind": "paper", "url": "https://arxiv.org/abs/2607.04610"}, {"kind": "website", "url": "https://berkeleyautomation.github.io/robovista/"}], "authors": ["Shuangyu Xie", "Kaiyuan Chen", "Ziyang Chen", "Simeon Adebola", "Yixuan Huang", "Zehan Ma", "Tianshuang Qiu", "Wentao Yuan", "Dhruv Shah", "Pannag R. Sanketi", "Ken Goldberg"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.04610", "source_url": "https://arxiv.org/abs/2607.04610"}, "categories": ["Robotics", "Robotics & Embodied AI"], "description": {"en": "RoboVista evaluates vision-language models on robot question answering with 474 visual question answering instances spanning 39 task types across agricultural, industrial, domestic, surgical, and autonomous driving domains."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.04610", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.04610", "title": "RoboVista"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2607.04610", "modality": null, "name": "RoboVista", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "High", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "unknown", "origin_record_id": "bm_robovista_4b4e3ac7", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "6e7045d26b09ef2b344d00e59b2b422fb59d0ef6a8275dd18ec5dd09c780e94f", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.04610"}, "publisher": null, "released": "2026-07-06", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.04610", "source_url": "https://arxiv.org/abs/2607.04610"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-04610", "source": "claire_radar", "source_benchmark_id": "2607.04610", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Robotics & Embodied AI"], "area": "Robotics & Embodied AI", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2607.04610", "observedAt": "2026-10-04T03:02:42.754940Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "status": "unavailable"}, "capabilities": [], "confidence": "High", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "309dd1beb54804291eca7401b61f4e0b37428c9ffacb78a60113abaf55e93255", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "RoboVista evaluates vision-language models on robot question answering with 474 visual question answering instances spanning 39 task types across agricultural, industrial, domestic, surgical, and autonomous driving domains.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "We propose Robot Question Answering (RQA), a modular evaluation framework and RoboVista, a benchmark curated from real robotic systems, research papers, and expert annotations."}, "familyId": "bmf_3df0c5f42047", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_robovista_4b4e3ac7", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Robotics"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2607.04610", "paper": "https://arxiv.org/abs/2607.04610", "pdf": "https://arxiv.org/pdf/2607.04610", "project": "https://berkeleyautomation.github.io/robovista/", "report": "https://arxiv.org/abs/2607.04610"}, "metrics": [], "motivation": "Diverse applications for robotics, such as industry and agriculture, require robots to operate across various embodiments, changing visual conditions, and complex planning.", "name": "RoboVista", "oneLine": "RoboVista evaluates vision-language models on robot question answering with 474 visual question answering instances spanning 39 task types across agricultural, industrial, domestic, surgical, and autonomous driving domains.", "paperTitle": "RoboVista: Evaluating Vision Language Models for Diverse Robot Applications", "primaryDomain": "Robotics & Embodied AI", "publication": {"evidence": "Accepted to RSS 2026. Project website: https://berkeleyautomation.github.io/robovista/", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2607.04610", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "RSS 2026", "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Inspectable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-06", "source": {"authors": ["Shuangyu Xie", "Kaiyuan Chen", "Ziyang Chen", "Simeon Adebola", "Yixuan Huang", "Zehan Ma", "Tianshuang Qiu", "Wentao Yuan", "Dhruv Shah", "Pannag R. Sanketi", "Ken Goldberg"], "categories": ["cs.RO"], "id": "2607.04610", "title": "RoboVista: Evaluating Vision Language Models for Diverse Robot Applications", "type": "arxiv", "url": "https://arxiv.org/abs/2607.04610"}, "sourceUpdatedAt": "2026-07-06T02:34:56Z", "topics": ["Robotics"], "venueAttempts": [{"decisionRaw": "Accepted to RSS 2026. Project website: https://berkeleyautomation.github.io/robovista/", "evidence": [{"level": "author-claim", "observedAt": "2026-10-14T01:46:58.058199Z", "rawValue": "Accepted to RSS 2026. Project website: https://berkeleyautomation.github.io/robovista/", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2607.04610"}], "reviewStatus": "accepted", "venueName": "RSS 2026"}], "whyItMatters": "Robot applications require modular reasoning across diverse embodiments. This benchmark isolates decision components and shows correlation with real-world task execution, aiding VLM selection."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
